TEST #2535 RESULTS
02/04/2026 - 10:43 PM
ACCELERATOR
MODEL
108
tokens/s
generation
441
ms
time to first token
3091
tokens/s
prompt
911
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
AMD Ryzen 7 5700G with Radeon Graphics (znver3)
RAM
27.3GB
OS
Linux
Kernel Release
6.17.12-300.fc43.x86_64
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #1 SMP PREEMPT_DYNAMIC Sat Dec 13 05:06:24 UTC 2025
RUNTIME
Name
llamafile
Version
0.9.3
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
3787
tokens/s
139
tokens/s
278
ms
pp4096+tg256
2585
tokens/s
29.7
tokens/s
1.62
sec
pp2048+tg256
3233
tokens/s
52.2
tokens/s
644
ms
pp2048+tg768
3261
tokens/s
92.8
tokens/s
638
ms
pp1024+tg1024
3896
tokens/s
119
tokens/s
270
ms
pp1280+tg3072
3647
tokens/s
74.7
tokens/s
359
ms
pp384+tg1152
4035
tokens/s
144
tokens/s
101
ms
pp64+tg1024
1428
tokens/s
168
tokens/s
50
ms
pp16+tg1536
1949
tokens/s
153
tokens/s
13
ms